Ajeet Kumar Singh

Bio: Ajeet Kumar Singh is an academic researcher from Tata Consultancy Services. The author has contributed to research in topics: Sketch recognition & Sketch. The author has an hindex of 7, co-authored 10 publications receiving 153 citations. Previous affiliations of Ajeet Kumar Singh include International Institute of Information Technology, Hyderabad.

OCR-VQA: Visual Question Answering by Reading Text in Images

Abstract: The problem of answering questions about an image is popularly known as visual question answering (or VQA in short). It is a well-established problem in computer vision. However, none of the VQA methods currently utilize the text often present in the image. These "texts in images" provide additional useful cues and facilitate better understanding of the visual content. In this paper, we introduce a novel task of visual question answering by reading text in images, i.e., by optical character recognition or OCR. We refer to this problem as OCR-VQA. To facilitate a systematic way of studying this new problem, we introduce a large-scale dataset, namely OCRVQA-200K. This dataset comprises of 207,572 images of book covers and contains more than 1 million question-answer pairs about these images. We judiciously combine well-established techniques from OCR and VQA domains to present a novel baseline for OCR-VQA-200K. The experimental results and rigorous analysis demonstrate various challenges present in this dataset leaving ample scope for the future research. We are optimistic that this new task along with compiled dataset will open-up many exciting research avenues both for the document image analysis and the VQA communities.

Multilingual OCR for Indic Scripts

Abstract: In Indian scenario, a document analysis system has to support multiple languages at the same time. With emerging multilingualism in urban India, often bilingual, trilingual or even more languages need to be supported. This demands development of a multilingual OCR system which can work seamlessly across Indic scripts. In our approach the script is identified at word level, prior to the recognition of the word. An end-to-end RNN based architecture which can detect the script and recognize the text in a segmentation-free manner is proposed for this purpose. We demonstrate the approach for 12 Indian languages and English. It is observed that, even with the similar architecture, performance on Indian languages are poorer compared to English. We investigate this further. Our approach is evaluated on a large corpus comprising of thousands of pages. The Hindi OCR is compared with other popular OCRs for the language, as a further testimony for the efficacy of our method.

From Strings to Things: Knowledge-Enabled VQA Model That Can Read and Reason

Abstract: Text present in images are not merely strings, they provide useful cues about the image. Despite their utility in better image understanding, scene texts are not used in traditional visual question answering (VQA) models. In this work, we present a VQA model which can read scene texts and perform reasoning on a knowledge graph to arrive at an accurate answer. Our proposed model has three mutually interacting modules: i. proposal module to get word and visual content proposals from the image, ii. fusion module to fuse these proposals, question and knowledge base to mine relevant facts, and represent these facts as multi-relational graph, iii. reasoning module to perform a novel gated graph neural network based reasoning on this graph. The performance of our knowledge-enabled VQA model is evaluated on our newly introduced dataset, viz. text-KVQA. To the best of our knowledge, this is the first dataset which identifies the need for bridging text recognition with knowledge graph based reasoning. Through extensive experiments, we show that our proposed method outperforms traditional VQA as well as question-answering over knowledge base-based methods on text-KVQA.

Everything Is in the Name – A URL Based Approach for Phishing Detection

Abstract: Phishing attack, in which a user is tricked into revealing sensitive information on a spoofed website, is one of the most common threat to cybersecurity. Most modern web browsers counter phishing attacks using a blacklist of confirmed phishing URLs. However, one major disadvantage of the blacklist method is that it is ineffective against newly generated phishes. Machine learning based techniques that rely on features extracted from URL (e.g., URL length and bag-of-words) or web page (e.g., TF-IDF and form fields) are considered to be more effective in identifying new phishing attacks. The main benefit of using URL based features over page based features is that the machine learning model can classify new URLs on-the-fly even before the page is loaded by the web browser, thus avoiding other potential dangers such as drive-by download attacks and cryptojacking attacks.

Towards a Robust OCR System for Indic Scripts

Abstract: The current Optical Character Recognition OCR systems for Indic scripts are not robust enough for recognizing arbitrary collection of printed documents. Reasons for this limitation includes the lack of resources (e.g. not enough examples with natural variations, lack of documentation available about the possible font/style variations) and the architecture which necessitates hard segmentation of word images followed by an isolated symbol recognition. Variations among scripts, latent symbol to UNICODE conversion rules, non-standard fonts/styles and large degradations are some of the major reasons for the unavailability of robust solutions. In this paper, we propose a web based OCR system which (i) follows a unified architecture for seven Indian languages, (ii) is robust against popular degradations, (iii) follows a segmentation free approach, (iv) addresses the UNICODE re-ordering issues, and (v) can enable continuous learning with user inputs and feedbacks. Our system is designed to aid the continuous learning while being usable i.e., we capture the user inputs (say example images) for further improving the OCRs. We use the popular BLSTM based transcription scheme to achieve our target. This also enables incremental training and refinement in a seamless manner. We report superior accuracy rates in comparison with the available OCRs for the seven Indian languages.

ICDAR2017 Robust Reading Challenge on Multi-Lingual Scene Text Detection and Script Identification - RRC-MLT

Abstract: Text detection and recognition in a natural environment are key components of many applications, ranging from business card digitization to shop indexation in a street. This competition aims at assessing the ability of state-of-the-art methods to detect Multi-Lingual Text (MLT) in scene images, such as in contents gathered from the Internet media and in modern cities where multiple cultures live and communicate together. This competition is an extension of the Robust Reading Competition (RRC) which has been held since 2003 both in ICDAR and in an online context. The proposed competition is presented as a new challenge of the RRC. The dataset built for this challenge largely extends the previous RRC editions in many aspects: the multi-lingual text, the size of the dataset, the multi-oriented text, the wide variety of scenes. The dataset is comprised of 18,000 images which contain text belonging to 9 languages. The challenge is comprised of three tasks related to text detection and script classification. We have received a total of 16 participations from the research and industrial communities. This paper presents the dataset, the tasks and the findings of this RRC-MLT challenge.

ICDAR2019 Robust Reading Challenge on Multi-lingual Scene Text Detection and Recognition — RRC-MLT-2019

Abstract: With the growing cosmopolitan culture of modern cities, the need of robust Multi-Lingual scene Text (MLT) detection and recognition systems has never been more immense. With the goal to systematically benchmark and push the state-of-the-art forward, the proposed competition builds on top of the RRC-MLT-2017 with an additional end-to-end task, an additional language in the real images dataset, a large scale multi-lingual synthetic dataset to assist the training, and a baseline End-to-End recognition method. The real dataset consists of 20,000 images containing text from 10 languages. The challenge has 4 tasks covering various aspects of multi-lingual scene text: (a) text detection, (b) cropped word script classification, (c) joint text detection and script classification and (d) end-to-end detection and recognition. In total, the competition received 60 submissions from the research and industrial communities. This paper presents the dataset, the tasks and the findings of the presented RRC-MLT-2019 challenge.

GIT: A Generative Image-to-text Transformer for Vision and Language

Abstract: In this paper, we design and train a Generative Image-to-text Transformer, GIT, to unify vision-language tasks such as image/video captioning and question answering. While generative models provide a consistent network architecture between pre-training and fine-tuning, existing work typically contains complex structures (uni/multi-modal encoder/decoder) and depends on external modules such as object detectors/taggers and optical character recognition (OCR). In GIT, we simplify the architecture as one image encoder and one text decoder under a single language modeling task. We also scale up the pre-training data and the model size to boost the model performance. Without bells and whistles, our GIT establishes new state of the arts on 12 challenging benchmarks with a large margin. For instance, our model surpasses the human performance for the first time on TextCaps (138.2 vs. 125.5 in CIDEr). Furthermore, we present a new scheme of generation-based image classification and scene text recognition, achieving decent performance on standard benchmarks. Codes are released at \url{https://github.com/microsoft/GenerativeImage2Text}.

Script identification in natural scene image and video frames using an attention based Convolutional-LSTM network

Abstract: Script identification plays a significant role in analysing documents and videos. In this paper, we focus on the problem of script identification in scene text images and video scripts. Because of low image quality, complex background and similar layout of characters shared by some scripts like Greek, Latin, etc., text recognition in those cases become challenging. In this paper, we propose a novel method that involves extraction of local and global features using CNN-LSTM framework and weighting them dynamically for script identification. First, we convert the images into patches and feed them into a CNN-LSTM framework. Attention-based patch weights are calculated applying softmax layer after LSTM. Next, we do patch-wise multiplication of these weights with corresponding CNN to yield local features. Global features are also extracted from last cell state of LSTM. We employ a fusion technique which dynamically weights the local and global features for an individual patch. Experiments have been done in four public script identification datasets: SIW-13, CVSI2015, ICDAR-17 and MLe2e. The proposed framework achieves superior results in comparison to conventional methods.

Iterative Answer Prediction With Pointer-Augmented Multimodal Transformers for TextVQA

Abstract: Many visual scenes contain text that carries crucial information, and it is thus essential to understand text in images for downstream reasoning tasks. For example, a deep water label on a warning sign warns people about the danger in the scene. Recent work has explored the TextVQA task that requires reading and understanding text in images to answer a question. However, existing approaches for TextVQA are mostly based on custom pairwise fusion mechanisms between a pair of two modalities and are restricted to a single prediction step by casting TextVQA as a classification task. In this work, we propose a novel model for the TextVQA task based on a multimodal transformer architecture accompanied by a rich representation for text in images. Our model naturally fuses different modalities homogeneously by embedding them into a common semantic space where self-attention is applied to model inter- and intra- modality context. Furthermore, it enables iterative answer decoding with a dynamic pointer network, allowing the model to form an answer through multi-step prediction instead of one-step classification. Our model outperforms existing approaches on three benchmark datasets for the TextVQA task by a large margin.